microllm-50m:latest
OLLAMA GGUFllama · 49.31M · F16
Jun 28, 2026 · Apple M4 Pro
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
Global Score
28 vs 83
Hardware Fit
80 vs 60
Quality Score
5 vs 93
Hardware
microllm-50m:latest gemma4:31b
MachineMac miniASUSTeK COMPUTER INC. GX10
CPUApple M4 ProCortex-X925
Cores1220
RAM24 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
microllm-50m:latest gemma4:31b
Tokens/sec1000000.010.9
First chunk50 ms681 ms
TTFT30.0 s681 ms
Load time0.3 s16.6 s
Memory usage0.1 GB21.4 GB
Memory %1%18%
HW Fit Score Breakdown
microllm-50m:latest
Speed
50/50
TTFT
0/20
Memory
30/30
gemma4:31b
Speed
10/50
TTFT
20/20
Memory
30/30
Quality
microllm-50m:latest
Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest